paper
referenced-only
2021
paper:wang-2021-beta-crownBeta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Verification
ByShiqi Wang·Huan Zhang·Kaidi Xu·Xue Lin·S. Jana·Cho-Jui Hsieh+1 more
Similar preprints — Semantic Scholar
Cited by (1)
- Adversarial Examples Are Not Bugs, They Are Superposition
Superposition causally contributes to adversarial vulnerability, and the link runs in both directions: in a toy ReLU autoencoder (n=100 features, m=20 hidden units), raising feature sparsity raises fe